Study on the method of precise entity search based on Baidu’s query
For a given query,searching for entities that conform to the description facts in the given set,in view of this goal,this paper proposes a matching method based on classification and semantic extension.The algorithm firstly to classify the query string into three categories,and extract the key word of different categories of query word.Then the keyword is extended to get the matching word set based on the word2vec word vector model.At last we calculate the score of every entity by the weighted matching method and get results accord-ing to the score ranking.After the experiment,the method get the correct rate of 63.2%,which has good applicability,and to a certain extent,it reduces the re-trieval failure rate due to the query of the spoken language and diversification.
entity search word2vec precise matching similarity
Teng Wang Xueqiang Lv Xun Ma Pengyan Sun Zhian Dong Jianshe Zhou
Beijing Key Laboratory of Internet Culture and Digital Dissemination Research,Beijing Information Sc Beijing Advanced Innovation Center for Imaging Technology,Capital Normal University,Beijing,China
国际会议
第五届自然语言处理与中文计算会议(NLPCC-ICCPOL2016)
昆明
英文
1-8
2016-12-02（万方平台首次上网日期，不代表论文的发表时间）